SARIMA Modelling Approach for Forecasting of Traffic Accidents

Road traffic mortality in Iran: longitudinal trend and seasonal analysis, March 2011-February 2020

Road traffic mortalities (RTMs) and injuries are among the leading causes of human fatalities worldwide, particularly in low-and middle-income countries like Iran. Using an interrupted time series analysis, we investigated three interventional points (two government-mandated fuel price increases and increased traffic ticket fines) for their potential relation to RTMs. Our findings showed that while the overall trend of RTMs was decreasing during the study period, multiple individual provinces showed smaller reductions in RTMs. We also found that both waves of government-mandated fuel price increases coincided with decreases in RTMs. However, the second wave coincided with RTM decreases in a smaller number of provinces than the first wave suggesting that the same type of intervention may not be as effective when repeated. Also, increased traffic ticket fines were only effective in a small number of provinces. Potential reasons and solutions for the findings are discussed in light of Iran's Road Safety Strategic Plan.

Exploration of the application of Grey-Markov models in the causality analysis of traffic accidents in roundabouts

We propose a multivariate Grey-Markov model to quantify traffic accident risk from different causality factors in roundabouts that is uniquely suited for the scarce and stochastic traffic crash data from roundabouts. A data sample of traffic crashes occurring in roundabouts in the U.S. State of Michigan from 2016 to 2021 was collected to investigate the capabilities of this modeling methodology. The multivariate grey model (MGM(1,4)) was constructed using grey relational analysis to determine the best dimensions for model optimization. Then, the Markov chain is introduced to address the unfitness of stochastic, fluctuating data in the MGM(1,4) model. Finally, our proposed hybrid MGM(1,4)-Markov model is compared with other models and validated. This study highlights the superior predictive performance of our MGM(1,4)-Markov model in fore-casting roundabout traffic accidents under data-limited conditions, achieving a 3.02% accuracy rate, in contrast to the traditional GM(1,1) model at 8.30% and the MGM(1,4) model at 4.47%. Moreover, incorporating human, vehicle, and environmental risk factors into a multivariate crash system yields more accurate predictions than merely aggregating crash counts.

The spatiotemporal prediction method of urban population density distribution through behaviour environment interaction agent model

Based on the interrelationship between the built environment and spatial-temporal distribution of population density, this paper proposes a method to predict the spatial-temporal distribution of urban population density using the depth residual network model (ResNet) of neural network. This study used the time-sharing data of mobile phone users provided by the China Mobile Communications Corporation to predict the time-space sequence of the steady-state distribution of population density. Firstly, 40 prediction databases were constructed according to the characteristics of built environment and the spatial-temporal distribution of population density. Thereafter, the depth residual model ResNet was used as the basic framework to construct the behaviour-environment agent model (BEM) for model training and prediction. Finally, the average percentage error index was used to evaluate the prediction results. The results revealed that the accuracy rate of prediction results reached 76.92% in the central urban area of the verification case. The proposed method can be applied to prevent urban public safety incidents and alleviate pandemics. Moreover, this method can be practically applied to enable the construction of a "smart city" for improving the efficient allocation of urban resources and traffic mobility.

The influence of the COVID-19 pandemic on identifying HIV/AIDS cases in China: an interrupted time series study

Background

The COVID-19 pandemic has caused significant global public health challenges, and impacted HIV testing and reporting worldwide. We aimed to estimate the impact of COVID-19 polices on identifying HIV/AIDS cases in China from 2020 to 2022.

Methods

We used an interrupted time series (ITS) design and seasonal autoregressive integrated moving average intervention (SARIMA Intervention) model. Monthly reported data on HIV/AIDS cases were extracted from the National Bureau of Disease Control and Prevention of China from January 2004 to August 2022. Data on Stringency Index (SI) and Economic Support Index (ESI) from January 22, 2020 to August 31, 2022 were extracted from the Oxford COVID-19 Government Response Tracker (OxCGRT). Using these, a SARIMA-Intervention model was constructed to evaluate the association between COVID-19 polices and monthly reported HIV/AIDS case numbers from January 2004 to August 2022 using auto.arima () function from R. The absolute percentage errors (APEs) compared the expected numbers generated by the SARIMA-Intervention model with actual numbers of HIV/AIDS, and was the primary outcome of this study. A second counterfactual model estimated HIV/AIDS case numbers if COVID-19 hadn't occurred in December 2019, and the mean difference between actual and predicted numbers were calculated. All statistical analyses were performed in R software (version 4.2.1) and EmpowerStats 2.0 and a P < 0.05 was considered statistically significant.

Findings

The SARIMA-Intervention model indicated HIV/AIDS monthly reported cases were inversely and significantly correlated with stricter lockdown and COVID-19 related polices (Coefficient for SI = -231.24, 95% CI: -383.17, -79.32) but not with economic support polices (Coefficient for ESI = 124.27, 95% CI: -309.84, 558.38). APEs of the SARIMA-Intervention model for prediction of HIV/AIDS cases from January 2022 through August 2022, were -2.99, 5.08, -13.64, -34.04, -2.76, -1.52, -1.37 and -2.47 respectively, indicating good accuracy and underreporting of cases during COVID-19. The counterfactual model estimates between January 2020 and August 2022 an additional 1314 HIV/AIDS cases should have been established monthly if COVID-19 hadn't occurred.

Interpretation

The COVID-19 pandemic influenced the allocation and acquisition of medical resources which impacted accurate monthly reporting of HIV in China. Interventions that promote continuous HIV testing and ensure the adequate provision of HIV services including remote delivery of HIV testing services (HIV self-testing) and online sexual counseling services are necessary during pandemics in future.

Funding

Ministry of Science and Technology of the People's Republic of China (The grant number: 2020YFC0846300) and Fogarty International Center, National Institutes of Health, USA (The grant number: G11TW010941).

SARIMA Model Forecasting Performance of the COVID-19 Daily Statistics in Thailand during the Omicron Variant Epidemic

This study aims to identify and evaluate a robust and replicable public health predictive model that can be applied to the COVID-19 time-series dataset, and to compare the model performance after performing the 7-day, 14-day, and 28-day forecast interval. The seasonal autoregressive integrated moving average (SARIMA) model was developed and validated using a Thailand COVID-19 open dataset from 1 December 2021 to 30 April 2022, during the Omicron variant outbreak. The SARIMA model with a non-statistically significant p-value of the Ljung–Box test, the lowest AIC, and the lowest RMSE was selected from the top five candidates for model validation. The selected models were validated using the 7-day, 14-day, and 28-day forward-chaining cross validation method. The model performance matrix for each forecast interval was evaluated and compared. The case fatality rate and mortality rate of the COVID-19 Omicron variant were estimated from the best performance model. The study points out the importance of different time interval forecasting that affects the model performance.